aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/perf_event.h
diff options
context:
space:
mode:
authorSong Liu <songliubraving@fb.com>2021-09-10 11:33:50 -0700
committerAlexei Starovoitov <ast@kernel.org>2021-09-13 10:53:50 -0700
commitc22ac2a3d4bd83411ebf0b1726e9e5fc4f5e7ebf (patch)
tree5a4286065571c6433ae43c49182fd8bbb9406c32 /include/linux/perf_event.h
parentselftests/bpf: Test new __sk_buff field hwtstamp (diff)
downloadlinux-dev-c22ac2a3d4bd83411ebf0b1726e9e5fc4f5e7ebf.tar.xz
linux-dev-c22ac2a3d4bd83411ebf0b1726e9e5fc4f5e7ebf.zip
perf: Enable branch record for software events
The typical way to access branch record (e.g. Intel LBR) is via hardware perf_event. For CPUs with FREEZE_LBRS_ON_PMI support, PMI could capture reliable LBR. On the other hand, LBR could also be useful in non-PMI scenario. For example, in kretprobe or bpf fexit program, LBR could provide a lot of information on what happened with the function. Add API to use branch record for software use. Note that, when the software event triggers, it is necessary to stop the branch record hardware asap. Therefore, static_call is used to remove some branch instructions in this process. Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/bpf/20210910183352.3151445-2-songliubraving@fb.com
Diffstat (limited to 'include/linux/perf_event.h')
-rw-r--r--include/linux/perf_event.h23
1 files changed, 23 insertions, 0 deletions
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fe156a8170aa..0cbc5dfe1110 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -57,6 +57,7 @@ struct perf_guest_info_callbacks {
#include <linux/cgroup.h>
#include <linux/refcount.h>
#include <linux/security.h>
+#include <linux/static_call.h>
#include <asm/local.h>
struct perf_callchain_entry {
@@ -1612,4 +1613,26 @@ extern void __weak arch_perf_update_userpage(struct perf_event *event,
extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr);
#endif
+/*
+ * Snapshot branch stack on software events.
+ *
+ * Branch stack can be very useful in understanding software events. For
+ * example, when a long function, e.g. sys_perf_event_open, returns an
+ * errno, it is not obvious why the function failed. Branch stack could
+ * provide very helpful information in this type of scenarios.
+ *
+ * On software event, it is necessary to stop the hardware branch recorder
+ * fast. Otherwise, the hardware register/buffer will be flushed with
+ * entries of the triggering event. Therefore, static call is used to
+ * stop the hardware recorder.
+ */
+
+/*
+ * cnt is the number of entries allocated for entries.
+ * Return number of entries copied to .
+ */
+typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries,
+ unsigned int cnt);
+DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t);
+
#endif /* _LINUX_PERF_EVENT_H */